fix: prevent eval.sh from exiting before writing reward.txt on score==0

oracle_checks.py exits with code 1 when composite score == 0.
set -euo pipefail in eval.sh caused the script to exit without writing
reward.txt, producing RewardFileNotFoundError in Harbor.

Add || true to the SCORE=$(...) line across all 12 MCP-unique eval.sh
scripts so the script continues to write reward.txt regardless of the
oracle score.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Author: sjarmak

benchmarks/ccb_mcp_crossorg/ccx-crossorg-061/tests/eval.sh

@@ -51,7 +51,7 @@ if [ ! -f "$ORACLE_CHECKS" ]; then
 fi
 
 echo "Running oracle checks..."
-SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1)
+SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1) || true
 
 # Validate score is a number
 if ! echo "$SCORE" | python3 -c "import sys; float(sys.stdin.read().strip())" 2>/dev/null; then

benchmarks/ccb_mcp_crossorg/ccx-crossorg-066/tests/eval.sh

@@ -51,7 +51,7 @@ if [ ! -f "$ORACLE_CHECKS" ]; then
 fi
 
 echo "Running oracle checks..."
-SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1)
+SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1) || true
 
 # Validate score is a number
 if ! echo "$SCORE" | python3 -c "import sys; float(sys.stdin.read().strip())" 2>/dev/null; then

benchmarks/ccb_mcp_crossrepo_tracing/ccx-config-trace-010/tests/eval.sh

@@ -51,7 +51,7 @@ if [ ! -f "$ORACLE_CHECKS" ]; then
 fi
 
 echo "Running oracle checks..."
-SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1)
+SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1) || true
 
 # Validate score is a number
 if ! echo "$SCORE" | python3 -c "import sys; float(sys.stdin.read().strip())" 2>/dev/null; then

benchmarks/ccb_mcp_crossrepo_tracing/ccx-dep-trace-001/tests/eval.sh

@@ -51,7 +51,7 @@ if [ ! -f "$ORACLE_CHECKS" ]; then
 fi
 
 echo "Running oracle checks..."
-SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1)
+SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1) || true
 
 # Validate score is a number
 if ! echo "$SCORE" | python3 -c "import sys; float(sys.stdin.read().strip())" 2>/dev/null; then

benchmarks/ccb_mcp_crossrepo_tracing/ccx-dep-trace-004/tests/eval.sh

@@ -51,7 +51,7 @@ if [ ! -f "$ORACLE_CHECKS" ]; then
 fi
 
 echo "Running oracle checks..."
-SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1)
+SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1) || true
 
 # Validate score is a number
 if ! echo "$SCORE" | python3 -c "import sys; float(sys.stdin.read().strip())" 2>/dev/null; then

benchmarks/ccb_mcp_incident/ccx-incident-031/tests/eval.sh

@@ -51,7 +51,7 @@ if [ ! -f "$ORACLE_CHECKS" ]; then
 fi
 
 echo "Running oracle checks..."
-SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1)
+SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1) || true
 
 # Validate score is a number
 if ! echo "$SCORE" | python3 -c "import sys; float(sys.stdin.read().strip())" 2>/dev/null; then

benchmarks/ccb_mcp_onboarding/ccx-explore-042-ds/tests/eval.sh

@@ -52,7 +52,7 @@ if [ ! -f "$ORACLE_CHECKS" ]; then
 fi
 
 echo "Running oracle checks..."
-SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1)
+SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1) || true
 
 # Validate score is a number
 if ! echo "$SCORE" | python3 -c "import sys; float(sys.stdin.read().strip())" 2>/dev/null; then

benchmarks/ccb_mcp_onboarding/ccx-onboard-041/tests/eval.sh

@@ -51,7 +51,7 @@ if [ ! -f "$ORACLE_CHECKS" ]; then
 fi
 
 echo "Running oracle checks..."
-SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1)
+SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1) || true
 
 # Validate score is a number
 if ! echo "$SCORE" | python3 -c "import sys; float(sys.stdin.read().strip())" 2>/dev/null; then

benchmarks/ccb_mcp_onboarding/ccx-onboard-050-ds/tests/eval.sh

@@ -52,7 +52,7 @@ if [ ! -f "$ORACLE_CHECKS" ]; then
 fi
 
 echo "Running oracle checks..."
-SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1)
+SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1) || true
 
 # Validate score is a number
 if ! echo "$SCORE" | python3 -c "import sys; float(sys.stdin.read().strip())" 2>/dev/null; then

benchmarks/ccb_mcp_platform/ccx-explore-091-ds/tests/eval.sh

@@ -52,7 +52,7 @@ if [ ! -f "$ORACLE_CHECKS" ]; then
 fi
 
 echo "Running oracle checks..."
-SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1)
+SCORE=$(python3 "$ORACLE_CHECKS" --answer "$ANSWER_PATH" --spec "$TASK_SPEC_PATH" --verbose 2>&1 | tee /dev/stderr | tail -1) || true
 
 # Validate score is a number
 if ! echo "$SCORE" | python3 -c "import sys; float(sys.stdin.read().strip())" 2>/dev/null; then